Development and validation of a predictive model for diarrhea in ICU patients with enteral nutrition
Qiuchan Chen, Yuzhen Chen, Haiqin Wang, Jing Huang, Xiuli Ou, Jieshan Hu, Xiaohong Yao, Lijun Guan
Abstract
BACKGROUND: The aim of this study was to build and validate a risk prediction model for diarrhea in patients in the intensive care unit (ICU) receiving enteral nutrition (EN) by identifying risk factors for diarrhea in these patients. METHODS: The risk factors for diarrhea were analyzed to build a prediction model for EN diarrhea in patients in the ICU based on the data collected from 302 patients receiving EN in the ICU. Subsequently, the model was validated by the area under the curve. RESULTS: In this study, the collected data were divided into two groups: a derivation cohort and a validation cohort. The results showed that 54.03% (114) of patients had diarrhea in the derivation cohort and 56.04% (51) of patients had diarrhea in the validation cohort. Moreover, days of EN, high urea nitrogen levels, probiotics, respiratory system disease, and daily doses of nutrient solution were included as predictive factors for diarrhea in patients receiving EN in the ICU. The predictive power of the model was 0.81 (95% CI, 0.752~0.868) in the derivation cohort and 0.736 (95% CI, 0.634~0.837) in the validation cohort. CONCLUSION: In accordance with the predictive factors, the model, characterized by excellent discrimination and high accuracy, can be used to clinically identify patients in the ICU with a high risk of EN diarrhea.